argument# error

[TalibDaryabi]

I tried to use LLaVa-1.1.0 , LLaVa-1.1.1, LLaVa-1.1.3,

With all of the above versions, I get the same error, but if I use LLaVa-1.2.0, I get the cache layer error, already raised as an issue.

Could you please let us know what could be the issue and how we can solve it? what was the version used with the paper?

e_downloadis deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, useforce_download=True`.
warnings.warn(
Loading checkpoint shards: 100%|██████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:18<00:00, 6.10s/it]
0%| | 0/18 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/Projects/Prompt-Highlighter/examples/llava_test.py", line 271, in
eval_model(args)
File "/Projects/Prompt-Highlighter/examples/llava_test.py", line 175, in eval_model
output_ids = model.generate(
File "/private/conda/envs/highlighter_2/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "private/conda/envs/highlighter_2/lib/python3.10/site-packages/transformers/generation/utils.py", line 1538, in generate
return self.greedy_search(
File "private/conda/envs/highlighter_2/lib/python3.10/site-packages/transformers/generation/utils.py", line 2362, in greedy_search
outputs = self(
File "/private/conda/envs/highlighter_2/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File /Projects/Prompt-Highlighter/./highlighter_modules/attention_llama_llava.py", line 248, in llava_hl_forward
) = self.prepare_inputs_labels_for_multimodal(
TypeError: LlavaMetaForCausalLM.prepare_inputs_labels_for_multimodal() takes 6 positional arguments but 7 were given